Image segmentation method converting unsupervised cluster into self-supervised classification

Abstract

The invention provides an image segmentation method converting an unsupervised cluster into a self-supervised classification. The method comprises the flowing sequentially executed steps that firstly, specific samples are extracted from an image and used as training samples through a fuzzy C-means method according to the characteristics of the samples, and an unsupervised clustering problem is converted into a self-supervised classification problem; secondly, subspace partition is carried out on the samples on the basis that the unsupervised clustering problem is converted into the self-supervised classification problem, and therefore an independent subspace is generated for each class of the self-supervised classification; thirdly, category classification is carried out on other samples except the specific samples in an iteration process with the help of KL conversion of multiple subspaces on the basis of the partitioned subspaces.

Description

technical field [0001] The invention relates to an image segmentation method for converting non-supervised clustering into self-supervised classification. Background technique [0002] There are two types of image segmentation: complete segmentation and partial segmentation. Complete segmentation has a great impact on the subsequent processing of images, so the requirements are relatively high. However, full segmentation is based on partial segmentation, which is a means of forming homomorphic regions for a certain feature, which do not directly correspond to objects in the image. In order to obtain a high-level complete segmentation from an image, partial segmentation can be performed first, and then based on it, high-level knowledge related to image content can be used for processing. Segmentation based on texture features belongs to the partial segmentation method in image segmentation. It uses texture features that can better describe the local pixel distribution struct...

AI Technical Summary

Problems solved by technology

[0004] Although some research results have been achieved in texture image segmentation based on pixel feature clustering methods, the segmentation results are sometimes unacceptable due to the diversity and irregularity of textures.

Images